state: generation 5084 (cycle)
This commit is contained in:
@@ -1317,7 +1317,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T08:53:22.614813+00:00",
|
||||
"generatedAt": "2026-09-10T08:56:25.949788+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
"10": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 360,
|
||||
"listingErrors": 361,
|
||||
"nextPage": 1,
|
||||
"recordsScanned": 0,
|
||||
"uniqueRecords": 0
|
||||
@@ -102,12 +102,12 @@
|
||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"failureLogsInspected": 0,
|
||||
"mode": "incremental_decision_only",
|
||||
"nextAccountIndex": 10,
|
||||
"nextAccountIndex": 11,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-10T08:53:22.590828+00:00",
|
||||
"updatedAt": "2026-09-10T08:56:25.925913+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T08:51:26.277216+00:00",
|
||||
"generatedAt": "2026-09-10T08:54:35.955651+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T08:45:45.905614+00:00",
|
||||
"lastSyncTime": "2026-09-10T08:45:45.454674+00:00",
|
||||
"generatedAt": "2026-09-10T08:54:23.705220+00:00",
|
||||
"lastSyncTime": "2026-09-10T08:54:23.346315+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1478,13 +1478,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 37,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 27,
|
||||
"ambiguous_runtime": 28,
|
||||
"framework_architecture_unsupported": 33,
|
||||
"memory_capacity": 1,
|
||||
"repository_structure": 1,
|
||||
"tokenizer_compatibility": 2
|
||||
},
|
||||
"failureCount": 64,
|
||||
"failureCount": 65,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -1494,8 +1494,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 64,
|
||||
"unresolvedFailureCount": 27
|
||||
"total": 65,
|
||||
"unresolvedFailureCount": 28
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 24,
|
||||
@@ -1911,29 +1911,29 @@
|
||||
"unresolvedFailureCount": 56
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 41,
|
||||
"decisionFailureRate": 0.9762,
|
||||
"decisionSuccessRate": 0.0238,
|
||||
"decisionTotal": 42,
|
||||
"attributableFailureCount": 42,
|
||||
"decisionFailureRate": 0.9767,
|
||||
"decisionSuccessRate": 0.0233,
|
||||
"decisionTotal": 43,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 22,
|
||||
"backend_operator": 23,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 4,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 57,
|
||||
"failureRate": 0.9828,
|
||||
"failureCount": 58,
|
||||
"failureRate": 0.9831,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0172,
|
||||
"successRate": 0.0169,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 58,
|
||||
"total": 59,
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Mthreads_s4000|llamacpp|text-generation": {
|
||||
@@ -2320,13 +2320,13 @@
|
||||
"unresolvedFailureCount": 842
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 233,
|
||||
"attributableFailureCount": 234,
|
||||
"decisionFailureRate": 0.9957,
|
||||
"decisionSuccessRate": 0.0043,
|
||||
"decisionTotal": 234,
|
||||
"decisionTotal": 235,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 153,
|
||||
"backend_operator": 27,
|
||||
"ambiguous_runtime": 154,
|
||||
"backend_operator": 28,
|
||||
"framework_architecture_unsupported": 169,
|
||||
"memory_capacity": 6,
|
||||
"model_load": 18,
|
||||
@@ -2336,15 +2336,15 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 21
|
||||
},
|
||||
"failureCount": 408,
|
||||
"failureCount": 410,
|
||||
"failureRate": 0.9976,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0024,
|
||||
"total": 409,
|
||||
"unresolvedFailureCount": 174
|
||||
"total": 411,
|
||||
"unresolvedFailureCount": 175
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2447,7 +2447,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T08:45:45.900554+00:00",
|
||||
"generatedAt": "2026-09-10T08:54:23.700725+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2478,7 +2478,7 @@
|
||||
"decisionSuccessRate": 0.05,
|
||||
"decisionTotal": 40,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 28,
|
||||
"ambiguous_runtime": 29,
|
||||
"framework_architecture_unsupported": 33,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 1,
|
||||
@@ -2487,15 +2487,15 @@
|
||||
"参数/模板问题": 11,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 252,
|
||||
"failureRate": 0.9921,
|
||||
"failureCount": 253,
|
||||
"failureRate": 0.9922,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0079,
|
||||
"total": 254,
|
||||
"unresolvedFailureCount": 214
|
||||
"successRate": 0.0078,
|
||||
"total": 255,
|
||||
"unresolvedFailureCount": 215
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 25,
|
||||
@@ -2654,27 +2654,27 @@
|
||||
"unresolvedFailureCount": 83
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 41,
|
||||
"decisionFailureRate": 0.8039,
|
||||
"decisionSuccessRate": 0.1961,
|
||||
"decisionTotal": 51,
|
||||
"attributableFailureCount": 42,
|
||||
"decisionFailureRate": 0.8077,
|
||||
"decisionSuccessRate": 0.1923,
|
||||
"decisionTotal": 52,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 22,
|
||||
"backend_operator": 23,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 4,
|
||||
"参数/模板问题": 17,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 113,
|
||||
"failureRate": 0.9187,
|
||||
"failureCount": 114,
|
||||
"failureRate": 0.9194,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0813,
|
||||
"total": 123,
|
||||
"successRate": 0.0806,
|
||||
"total": 124,
|
||||
"unresolvedFailureCount": 72
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -3525,15 +3525,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 12,
|
||||
"decisionFailureRate": 0.9231,
|
||||
"decisionSuccessRate": 0.0769,
|
||||
"decisionTotal": 13,
|
||||
"attributableFailureCount": 13,
|
||||
"decisionFailureRate": 0.9286,
|
||||
"decisionSuccessRate": 0.0714,
|
||||
"decisionTotal": 14,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 12
|
||||
"backend_operator": 13
|
||||
},
|
||||
"failureCount": 12,
|
||||
"failureRate": 0.9231,
|
||||
"failureCount": 13,
|
||||
"failureRate": 0.9286,
|
||||
"framework": "vllm",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
@@ -3541,10 +3541,10 @@
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 1,
|
||||
"successRate": 0.0769,
|
||||
"successRate": 0.0714,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 13,
|
||||
"total": 14,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors": {
|
||||
@@ -4015,21 +4015,21 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 7,
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 6,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 7,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 13,
|
||||
"framework_architecture_unsupported": 7
|
||||
"ambiguous_runtime": 14,
|
||||
"framework_architecture_unsupported": 6
|
||||
},
|
||||
"failureCount": 20,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T05:49:48.500487+00:00",
|
||||
"lastTerminalAt": "2026-09-10T08:54:23.346315+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4038,23 +4038,23 @@
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 13
|
||||
"unresolvedFailureCount": 14
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 4,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.875,
|
||||
"decisionSuccessRate": 0.125,
|
||||
"decisionTotal": 8,
|
||||
"decisionFailureRate": 0.8571,
|
||||
"decisionSuccessRate": 0.1429,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 8,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 4,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureRate": 0.9375,
|
||||
"failureCount": 14,
|
||||
"failureRate": 0.9333,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T06:11:26.144205+00:00",
|
||||
@@ -4062,10 +4062,10 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0625,
|
||||
"successRate": 0.0667,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 16,
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -6386,14 +6386,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|32": {
|
||||
"attributableFailureCount": 2,
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 2
|
||||
"backend_operator": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
@@ -6406,7 +6406,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|33": {
|
||||
@@ -6986,16 +6986,16 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1544,
|
||||
"totalRecords": 1631,
|
||||
"terminalRecords": 1546,
|
||||
"totalRecords": 1633,
|
||||
"totals": {
|
||||
"attributableFailureCount": 403,
|
||||
"decisionFailureRate": 0.8877,
|
||||
"decisionSuccessRate": 0.1123,
|
||||
"decisionTotal": 454,
|
||||
"attributableFailureCount": 404,
|
||||
"decisionFailureRate": 0.8879,
|
||||
"decisionSuccessRate": 0.1121,
|
||||
"decisionTotal": 455,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 320,
|
||||
"backend_operator": 32,
|
||||
"ambiguous_runtime": 321,
|
||||
"backend_operator": 33,
|
||||
"framework_architecture_unsupported": 271,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 46,
|
||||
@@ -7006,21 +7006,21 @@
|
||||
"参数/模板问题": 95,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1493,
|
||||
"failureCount": 1495,
|
||||
"failureRate": 0.967,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 51,
|
||||
"successRate": 0.033,
|
||||
"total": 1544,
|
||||
"unresolvedFailureCount": 1088
|
||||
"total": 1546,
|
||||
"unresolvedFailureCount": 1089
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -7028,7 +7028,7 @@
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -7049,6 +7049,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1631,
|
||||
"summarizedRecords": 1633,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T08:54:23.346315+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:49:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471916", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454624+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:41:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493673", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454539+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:39:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493671", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454585+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:37:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532019", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T18:56:39.802680+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T18:51:22+00:00", "targetGpu": "MetaX_c-500", "taskId": "4462836", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T18:43:35.404751+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T18:35:22+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4470642", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-07T16:24:49.011467+00:00", "modelId": "neuralmagic/granite-3.1-2b-instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T16:19:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080306", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-07T16:24:49.011435+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T16:17:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610399", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "25e9b57a569d834f102a80986de723659502eee6247c5be732049a5c3c6e7024",
|
||||
".modelhub_state/architecture_history_backfill.json": "42add55ebabfc13b464e6e26ad673d89ed75036d78f4ec7ca17ec3e368ced3d5",
|
||||
".modelhub_state/market_intelligence.json": "93aa555face11cc3e6375fcc4b1ad39251bd602aa521768b9d6b93a414c4e68d",
|
||||
".modelhub_state/official_capabilities.json": "ad472c478623c1fb33b31a9a352dcf50a2aae0ce61a67d205951ce12b8a2ee2d",
|
||||
".modelhub_state/outcome_checkpoint.json": "4db9914e3e885590345dc210f2f6d98f607a8913fc6f9dde16d1881aded1f3ed",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "9e1dd92103e660e1dbee0da5b937529385224c86d6eb3475c7cf34384111eafa",
|
||||
".modelhub_state/architecture_history_backfill.json": "cdbae33e4dd9e3b504fcbcd96a5530a24d0089b81b88f2f5e0356a8a6a8c1cd4",
|
||||
".modelhub_state/market_intelligence.json": "2047350ce4e2f8763cc69e5820fc28eda1bd7342e492d33a56a09c7ffa455cf6",
|
||||
".modelhub_state/official_capabilities.json": "b7406f37f493eefbcc44e48929a723ee3289907d3d406d49557492d0bbaceed1",
|
||||
".modelhub_state/outcome_checkpoint.json": "a6ed5a14e57587bb60603c109aacd43a4792955a19435865e995243013434861",
|
||||
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
|
||||
".modelhub_state/recent_outcomes.jsonl": "e50590432dedf4038724d96c819fa1c7b14b77c6ade9d4b126364f97608ca887",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "4722ab354c4813ec891e78e7cd7c0a74f26cf42ce964808b840ec64462046a20",
|
||||
".modelhub_state/recovery_intents.jsonl": "8030fdc15f4594ea51614a387b46c12cb9432e815a7d1bfe4b26a415d25db4a0",
|
||||
".modelhub_state/recent_outcomes.jsonl": "3f4eb3b80793d738a987d76dea4a148cd835934a25f6019d67e1c3a051be172a",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "8d5c49557f0961c8f07c6c1c47ed3f2310e2d75f6dc597a7987f69defaed9d1b",
|
||||
".modelhub_state/recovery_intents.jsonl": "186b610affa874dc8273dcb30cb713bc694552108b8c43771f749bc4989281e6",
|
||||
".modelhub_state/routing_intelligence.json": "8a52419d4402861a79d360da797632830eb2c915c1cd189832eea085096de774",
|
||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
||||
"ledger/submissions.jsonl": "1933ad805d1becf435394dbda5110270c499a0bd490635a19dc4240e65cfe8b1",
|
||||
"outcomes/submissions.jsonl": "8774b87840c4ce3a1250f08236dc7791dfeeb1436d1793886bb29a45328f3635"
|
||||
"outcomes/submissions.jsonl": "91fca38fede4537b5ee54c666edf87dc0a2de6ea7ea5ff03e2f533b115ba412e"
|
||||
},
|
||||
"generation": 5083,
|
||||
"generation": 5084,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-10T08:53:22.680741+00:00",
|
||||
"updatedAt": "2026-09-10T08:56:27.048671+00:00",
|
||||
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
||||
}
|
||||
|
||||
@@ -118,7 +118,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T17:46:46.041785+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20041566112, "estimatedRequiredGiB": 22.408, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 20050750527, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 20050750527}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:38:43.506267+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645748", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T17:46:46.041763+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:43:33.758884+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4645816", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T18:34:58.235126+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T10:33:51.484756+00:00", "targetGpu": "MetaX_c-500", "taskId": "4646505", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T19:13:04.549009+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5705684944, "estimatedRequiredGiB": 6.387, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5714910031, "modelscopeLicense": null, "modelscopeParams": 8031506432, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 5714910031}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T11:12:23.284350+00:00", "targetGpu": "MetaX_c-500", "taskId": "4647279", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T20:12:28.913845+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e023b149992af42872de3c0c0c07dafd6a98d965e5bdb5a29ec5869e58d45725", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.084154+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4648146", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T20:12:28.913909+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084014480, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093198689, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 9093198689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.097444+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648145", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T20:12:28.913926+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 31280205657, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 30554505408, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_moe", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31280205657}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.105603+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648141", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user